GNU Ocrad vs Open-Capture

GNU Ocrad is a free OCR program and library for Linux and self-hosted use. It reads PNG and PNM images and produces recognized text as 8-bit bytes or UTF-8. Its layout analyzer can separate columns and text blocks on printed pages. Ocrad runs as a standalone console application or as a backend for other programs. Documented options cover image transformations, layout detection, character recognition, text filters, and an OCR results file containing structured recognition details. The software uses ISO 10646 internally, with character-set selection through the --charset option. The manual recommends characters at least 20 pixels high and says 300 dpi scanning usually reaches a suitable size. It also notes sensitivity to character defects and difficulty adding recognition for new characters. The project describes Ocrad mainly as a research project, with algorithms that may change in later releases. Latest releases are available through GNU mirrors, while older and testing versions are hosted on Savannah.

Open-Capture collects documents, extracts information with OCR and AI, and exports results to third-party management software. It accepts material from scanners, copiers, file drops, email and attachments, web forms, uploads, and web services. Extraction options include Tesseract OCR, pre-trained models, machine-learning classification, key-value extraction, reference-data matching, dictionaries, and barcode or QR-code reading. Extracted fields can be checked against rules, formats, reference data, and scripted business rules. The full-web application runs natively on Linux and can be hosted on-premise or in a public or private cloud. It is free and open-source under the GNU GPLv3 license, with no limit on users. Optional modules include Splitter for preparing batches, Verifier for checking extracted data, and MailCollect for email processing. MailCollect analyzes messages, identifies senders, extracts metadata, and routes attachments into processing workflows. Verifier is described for structured or semi-structured documents such as invoices, delivery notes, contracts, and purchase orders. Listed connections include a native MEM Courrier connector, CMIS, OpenADS/Oxalis, OpenCRM, Alfresco, and SharePoint; export formats include PDF, PDF/A, XML, CSV, and plain text.